affine-mcp-server-integration

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the affine-mcp-server package from the npm registry and pull a container image from the GitHub Container Registry (ghcr.io/dawncr0w/affine-mcp-server). These are well-known, official services used for software distribution.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads external document content and database entries from AFFiNE workspaces into the agent's context.
  • Ingestion points: Untrusted data enters the agent context through tools like read_doc, search_docs, and list_comments described in SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters defined to separate ingested document content from the agent's system instructions.
  • Capability inventory: The skill provides extensive capabilities including file system-like operations (create_doc, update_doc, delete_doc) and administrative workspace tasks (create_workspace, delete_workspace) across various scripts referenced in the tool manifest.
  • Sanitization: No sanitization or validation mechanisms are mentioned for the content retrieved from external documents before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 01:04 AM
Security Audit — agent-trust-hub — affine-mcp-server-integration